cv

Ph.D.

George Mason University

Computer Science - AI and Robotics

• Advanced Machine Learning
• Deep Learning
• Reinforcement Learning
• Computer Vision

M.Sc.

Carnegie Mellon University

Mechanical Engineering

• Machine Learning
• Deep Learning
• Computer Vision
• Deep Reinforcement Learning & Control

B.S.

University of Cincinnati

Mechanical Engineering

Decremental Dynamics Planning for Robot Navigation

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

With Yuanjie Lu, Tong Xu, Nick Hawes, and Xuesu Xiao. Full-dynamics planning near the robot, simplified along the horizon; 1st place, simulation phase, 2025 BARN Challenge.

Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

First author, with Tong Xu, Yuanjie Lu, and Xuesu Xiao. Teacher-adapted auxiliary rewards; +2.35% navigation success, +122.62% off-road mobility, 3x faster training, 5/5 vs 2/5 physical-robot trials.

GACL: Grounded Adaptive Curriculum Learning with Active Task and Performance Monitoring

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

First author, with Zifan Xu, Peter Stone, and Xuesu Xiao. Grounded automatic curriculum generation for robotics; +6.8% success on wheeled navigation and +6.1% on quadruped locomotion over state of the art.

II-NVM: Enhancing Map Accuracy and Consistency with Normal Vector-Assisted Mapping

IEEE Robotics and Automation Letters (RA-L)

With Chengwei Zhao, Yixuan Li, Yina Jian, Jie Xu, Yongxin Ma, and Xinglai Jin. Normal-vector-consistent SLAM mapping resolving the double-sided mapping issue.

Software Development Engineer Intern - RDS Proxy Team

Amazon Web Services (AWS)

Performance testing and visualization infrastructure for RDS Proxy

• Built a Streamlit performance-analysis platform with 8 interactive visualization types, reducing regression analysis time from 8 hours to 15 minutes
• Developed a regression testing framework with rigorous statistics (Welch's t-test, power analysis, Bonferroni correction) for high-confidence regression detection
• Implemented adaptive sampling with Thompson Sampling and Bayesian optimization, improving test reliability from 47% to 90% and reducing false positives
• Integrated CloudWatch metrics into automated dashboards for multi-region performance monitoring

Graduate Research Assistant

RobotiXX Lab, George Mason University

Curriculum learning and reinforcement learning for robot navigation and locomotion, advised by Dr. Xuesu Xiao

• First author of two IROS 2025 papers (GACL, with Peter Stone; Reward Training Wheels); co-author of a third IROS 2025 paper (DDP) and an IEEE RA-L 2025 article (II-NVM)
• Developed GACL, a grounded adaptive curriculum framework improving success rates by 6.8% (wheeled navigation) and 6.1% (quadruped locomotion in confined 3D spaces) over state-of-the-art methods
• Designed Reward Training Wheels, teacher-adapted auxiliary rewards achieving 122.62% off-road mobility improvement, 3x faster training, and 5/5 vs 2/5 success in physical off-road trials
• Contributed to the DDP navigation system that won 1st place in the simulation phase of the 2025 BARN Challenge
• Trained massively parallel RL policies (PPO, SAC) in IsaacGym across wheeled, quadruped, and off-road platforms; ongoing work extends curriculum learning to humanoid robots

Research Assistant

Computational Engineering and Robotics Lab, CMU

3D AR scene inpainting via deep learning

• Developed an end-to-end deep learning pipeline for 3D AR scene inpainting achieving 92% scene-completion accuracy
• Fine-tuned a GAN-based image inpainting model, improving texture realism by 35% over baseline
• Applied RANSAC and DBSCAN for 3D point cloud segmentation, reducing processing time by 40%

Research Assistant

Bio-robotics Lab, CMU

Recycled paper classification with deep learning

• Trained a CNN classifier for recycled paper grading (97% accuracy on 10,000+ images) with a real-time OpenCV processing pipeline

Teaching Assistant — Introduction to Programming

George Mason University

Fall 2023

Teaching Assistant — Artificial Intelligence and Machine Learning

Carnegie Mellon University

Fall 2022

Teaching Assistant — System Dynamics, Fluid Dynamics and Engineering Models

University of Cincinnati

Fall 2020

1st Place, Simulation Phase — 2025 BARN Challenge (Benchmark Autonomous Robot Navigation)

ICRA 2025

DDP-based navigation system won the simulation phase of the BARN Challenge.